Objective Wearable inertial measurement unit(IMU)technology and random forest(RF)algorithm were used to detect the fatigue level of long-distance walking with backpack load.Moreover,the feasibility of fatigue detection for load-bearing walking and an optimal IMU combination scheme were evaluated.Methods Thirty healthy male college students were recruited for long-distance backpack walking.The Xsens MVN Link inertial motion capture system and Borg-RPE fatigue scale were used to collect the kinematic data and subjective fatigue values of load-bearing walking.These were divided into three levels:without fatigue,moderate fatigue,and severe fatigue.The original data were extracted;gait segmentation,data screening,and feature extraction were performed;and the RF model was used for the machine learning of sample features.Finally,the accuracy rate,precision,confusion matrix,and area under the curve(AUC)were calculated to evaluate the detection effects of the different IMU combinations.Results The accuracy of a right femur IMU was 82.55%and that of five IMU combinations was 87.94%.For a combination of IMUs,at least one upper-body IMU was included,and the left limb had more IMUs than the right limb.The RF model had a higher level of fatigue detection for load-bearing walking.When four IMUs were used,the AUCs of three-level fatigue were 0.99,0.97,and 0.99,respectively.Conclusions IMU technology and the RF algorithm have high accuracy and classification capability in the three-level fatigue detection task for walking with a backpack load.In practical applications,the use of one-five IMUs is recommended.Moreover,a combination of an upper-body IMU and a lower-limb IMU configuration scheme is preferred.
维普
万方数据
